Support radix cache for Lora feature (#7216)

python/sglang/srt/server_args.py

@@ -2004,11 +2004,7 @@ class ServerArgs:
         ), "chunked_prefill_size must be divisible by page_size"
 
     def check_lora_server_args(self):
-        assert (
-            self.max_loras_per_batch > 0
-            # FIXME
-            and (self.lora_paths is None or self.disable_radix_cache)
-        ), "compatibility of lora and radix attention is in progress"
+        assert self.max_loras_per_batch > 0, "max_loras_per_batch must be positive"
 
         # Enable LoRA if any LoRA paths are provided for backward compatibility.
         if self.lora_paths: